Instantaneous Gradient based Dual Mode Wavelet Neural Network Blind Equalization for Underwater Acoustic Channel

Authors

Ying XIAO, College of Information and Communication Engineering, Dalian Nationality University, 116600 Dalian, China\\ Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, 116600 Dalian, ChinaFollow
Yuhua DONG, College of Information and Communication Engineering, Dalian Nationality University, 116600 Dalian, ChinaFollow

Author Country (or Countries)

China

Abstract

To further improve the performance of wavelet neural network blind equalization based on constant modulus algorithm (CMA) cost function, an instantaneous gradient based dual mode between modified constant modulus algorithm (MCMA) and decision directed (DD) algorithm was proposed. The wavelet neural network weights change quantity of the adjacent iterative process is defined as instantaneous gradient. After the network attains convergence, the weights of wavelet neural network achieve a stable energy state and the instantaneous gradient would be zero. Therefore dual mode algorithm can be realized by criterion which set according to the instantaneous gradient. Computer simulation results show that the dual mode wavelet neural network blind equalization algorithm proposed in this paper improves the convergence rate and convergence precision effectively, and it has good tracking ability for underwater acoustic channel.

Recommended Citation

XIAO, Ying and DONG, Yuhua (2015) "Instantaneous Gradient based Dual Mode Wavelet Neural Network Blind Equalization for Underwater Acoustic Channel," Applied Mathematics & Information Sciences: Vol. 09: Iss. 3, Article 41.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol09/iss3/41